Deep-Learning Control of Lower-Limb Exoskeletons via simplified Therapist Input

2024-12-10

arXiv.org

AI Summary

To address the reliance of lower-limb exoskeletons on labor-intensive individual calibration and manual controller tuning during complex gait rehabilitation (e.g., stair climbing or ramp walking), this paper proposes a data-driven, lightweight three-layer control framework: (1) real-time gait state estimation; (2) therapist-interactable modulation of key kinematic features; and (3) joint prediction of joint poses and spring-damper parameters via deep learning with explicit uncertainty modeling. Its novelty lies in synergistically integrating intuitive therapist intervention with uncertainty-aware prediction, eliminating conventional hierarchical control’s dependence on subject-specific parameter optimization. Validated on treadmill and stair scenarios, the framework employs a state inference network, an interactive visualization interface, and a stiffness-kinematics joint mapping module. Experimental results demonstrate dynamic joint motion adaptation to therapist commands and negative interaction power—confirming active assistance capability and cross-task generalizability.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Partial-assistance exoskeletons hold significant potential for gait rehabilitation by promoting active participation during (re)learning of normative walking patterns. Typically, the control of interaction torques in partial-assistance exoskeletons relies on a hierarchical control structure. These approaches require extensive calibration due to the complexity of the controller and user-specific parameter tuning, especially for activities like stair or ramp navigation. To address the limitations of hierarchical control in exoskeletons, this work proposes a three-step, data-driven approach: (1) using recent sensor data to probabilistically infer locomotion states (landing step length, landing step height, walking velocity, step clearance, gait phase), (2) allowing therapists to modify these features via a user interface, and (3) using the adjusted locomotion features to predict the desired joint posture and model stiffness in a spring-damper system based on prediction uncertainty. We evaluated the proposed approach with two healthy participants engaging in treadmill walking and stair ascent and descent at varying speeds, with and without external modification of the gait features through a user interface. Results showed a variation in kinematics according to the gait characteristics and a negative interaction power suggesting exoskeleton assistance across the different conditions.

Problem

• Simplifies therapist input for exoskeleton control
• Reduces calibration needs in partial-assistance exoskeletons
• Improves adaptability for stair and ramp navigation

Innovation

• Probabilistic inference of locomotion states
• Therapist-modified features via interface
• Posture prediction using spring-damper system